← Back to all news
arXiv Machine Learning By Haolan Guo, Linwei Tao, Haoyang Luo, Minjing Dong, Chang Xu

Sample Margin-Aware Recalibration of Temperature Scaling

Read the original on arXiv Machine Learning →

The paper introduces SMART, a lightweight recalibration technique that adjusts logits based on the margin between the top two logits, called the logit gap. It uses a soft-binned Expected Calibration Error objective to balance bias and variance, enabling stable updates even with limited calibration data. Experiments across various datasets and architectures show SMART achieves state‑of‑the‑art calibration with fewer parameters than existing methods.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Jul 10

LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks

arXiv:2607. 07745v1 Announce Type: new Abstract: While accuracy, robustness, and calibration are all essential for reliable neural networks, they are often studied separately; developing models that satisfy all three simultaneously remains a central challenge.

By Arthur Chiron (IRIT, EPE UT), Franck Mamalet (IRIT, DTIPG - SNCF, UT3), Thomas Massena (IRIT, DTIPG - SNCF, UT3), Thomas Deltort (IRIT), Mathieu Serrurier (IRIT, UT2J)
benchmarks
More like this →
arXiv AI
Oct 12

Calibration in One Go: Jointly Learning Accurate and Calibrated Neural Networks

The paper proposes a bilevel Stackelberg formulation that trains standard post‑hoc calibrators end‑to‑end with the neural network backbone, eliminating the need for a separate calibration dataset or dedicated loss. By jointly optimizing accuracy and calibration with cross‑entropy and a single calibrator learning‑rate hyperparameter, the method can use any calibrator type, but shows that the final classification layer alone suffices to produce accurate, well‑calibrated models. This approach outperforms state‑of‑the‑art calibrators while adding minimal complexity and avoiding the overhead of separate calibration components, especially beneficial in multi‑task learning settings.

By Nektarios Kalampalikis, Pablo M. Olmos, Isabel Valera
benchmarks
More like this →